日本語版

AI Analysis Guide

AI/ML is the technology for extracting value from data. This skill systematically covers all aspects of AI analysis — from machine learning fundamentals, deep learning, natural language processing, and computer vision to practical model development workflows.

Target Audience

• Engineers seeking to systematically learn AI/ML fundamentals
• Those working on data analysis and predictive model development
• Professionals looking to leverage AI in their work

Prerequisites

• Basic knowledge of Python
• Foundational mathematics (concepts in linear algebra and probability/statistics)

Learning Guide

00-fundamentals — AI/ML Fundamentals

01-ml-basics — Machine Learning Basics

02-deep-learning — Deep Learning

03-practical — Practical Applications

Quick Reference

ML Algorithm Selection:
  Classification → Logistic Regression → Random Forest → XGBoost → NN
  Regression     → Linear Regression → Random Forest → XGBoost → NN
  Clustering     → k-means → DBSCAN → Hierarchical
  Dimensionality → PCA → t-SNE → UMAP
  Text           → Transformer → BERT → GPT
  Image          → CNN → ResNet → Vision Transformer

References

1. Goodfellow, I. et al. "Deep Learning." MIT Press, 2016.
2. Geron, A. "Hands-On Machine Learning." O'Reilly, 2022.
3. Vaswani, A. et al. "Attention Is All You Need." NeurIPS, 2017.